DIY Python Jarvis AI

Tired of 'free' api's for Text-To-Speech and Speech-To-Text that hardly let you use them? Tired of Paying you hard-earned developer cash for 404 api's which don't even exist? Tired of ALL the tutorials using Google APIs?

DON'T WORRY I GOTCHA

Yeah. So y'all might me knowing about Python, My 2^nd favourite language which you can install from here. I recommend you learn basics of python-3 before reading this blog. You can check out my other Python blogs too.

Prerequisites

We're using a popular Text-To-Speech wrapper called pyttsx3 and a speech recognition program called SpeechRecognition which you can install by opening Command Prompt(Windows), or Terminal (Linux, MacOS) , typing

pip install pyttsx3 SpeechRecognition

and pressing ENTER(return on Macbooks). On MacOS and go to Terminal and type

/bin/bash -c "$(curl -fsSL
        https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
        brew install portaudio espeak

For Ubuntu/Debian based linux, go to terminal and type sudo apt update && sudo apt install espeak ffmpeg libespeak1 then, press enter.

then press ENTER(return on Macbooks).

Pyttxs3 is a fairly simple to use if you have some basic knowledge of Python 3. There is some simple boilerplate to it. >>> import pyttxs3 >>> engine=pyttxs3.init() >>> engine.say("Some text to be spoken...") >>> engine.runAndWait()
engine=pyttxs3.init() creates the engine, engine.say("Some text to be spoken...") engine.runAndWait() basically says stuff in the in the engine.say("Customize what you want me to say.").

So Here's the code-

Code

I hope you lik this blog ; )